Positron Emission Tomography (PET) is an effective imaging technique to detect cancers, but interpretation of PET images is difficult for radiologists who have insufficient knowledge and experience. Radiologists could interpret PET images more effectively if they were able to share their PET expertise. To realize this goal, our recent efforts have designed a PET information model that represents the process of interpreting PET images; we have implemented the Whole-Body PET Database (WB-PET DB). The PET information model defines the WB-PET DB schema. WB-PET DB stores findings along with a region of interest (ROI), thereby allowing ROI image retrieval by keys that radiologists use when writing findings. Regarding WB-PET DB, we have shown its conceptual model in recent works, but have revealed little about its system architecture. In this study, we designed and implemented the WB-PET DB System. This system contains the user interface to insert ROI into WB-PET DB and the component that outputs results of retrieval. This component outputs them in a DICOM file format; thereby users can view stored ROIs using 3D visualization software such as AmiraTM. Results of this study demonstrated a model to retrieve an image of body functionality as a PET image.