This tutorial introduces the Medical Imaging OMOP extension (MI-CDM) and provides a practical, end-to-end guide for incorporating imaging data into OMOP-based observational research. While imaging features and radiomics are increasingly central to clinical and translational studies, imaging data remain largely siloed from EHR-derived data and are often difficult to make Findable, Accessible, Interoperable, and Reusable (FAIR). This tutorial demonstrates how the MI-CDM enables FAIR-aligned imaging research by representing DICOM metadata and derived imaging features within the OMOP CDM.  The session is designed for researchers, data scientists, informaticians, and OHDSI community members who want to launch their own imaging-enhanced OMOP dataset. Participants will gain hands-on experience to move from raw imaging archives to analysis-ready, multimodal data that integrate imaging, clinical, and demographic information.  We will begin with an overview of the MI-CDM design principles and how imaging concepts are harmonized with existing OMOP structures. The tutorial will then walk through a concrete workflow: indexing a clinical or research DICOM archive, extracting and characterizing DICOM metadata at scale, and transforming these metadata using standardized DICOM terminology, then loading them into searchable OMOP tables. Through this process, participants will experience how previously siloed imaging data—pixels and metadata—can be made findable.  Next, we will demonstrate how imaging-derived features can be added to the OMOP ecosystem. Using an example imaging algorithm, we will show how to generate quantitative imaging features and represent them within the OMOP data model, preserving provenance and supporting reuse.  Finally, the tutorial will demonstrate multimodal analytics using standard OHDSI tools. Participants will see how imaging features can be analyzed alongside clinical covariates using Atlas to perform data characterization and exploratory analyses. This step highlights how, within OMOP’s privacy-by-design framework, standardized queries can be executed without moving large image files, providing an accessible way to incorporate imaging data into traditional OMOP-based research workflows.  By the end of this tutorial, attendees will understand how to operationalize imaging within OMOP, apply FAIR principles to imaging research, and build imaging-enhanced datasets ready for observational and multimodal studies within the OHDSI ecosystem.