We describe an approach for retrieving threedimensional objects similar to a given one from a database. The key idea of our technique is to decompose each object into its meaningful components, and fit each component to a basic shape. This decomposition is represented as an attributed graph, which is considered the signature of the object. Our signature leverages human vision theories such as Marr's and Biederman's. We show that this signature gives rise to a retrieval algorithm which is invariant to non-rigid transformations. Finally, a system which realizes our technique was built and tested on a database of about 400 objects. The paper presents the retrieval results and conclusions are being drawn.