Due to the high performance of recent computer graphics hardware, 3D CG and CG animations have become in great demand for various applications. Many 3D models have already been created and stored. We need any 3D model search system that allows us to retrieve our required 3D models accurately. In this paper, the authors propose a 3D model search system that uses the attributed relational graph (ARG) of each 3D model, and that employs the stochastic ARG matching to measure the similarity among them. The proposed system gives better search results than those of D2 method in their experiments. This paper also describes what kinds of features of a 3D model are used as each vertex attributes for the stochastic ARG matching.