Ontology-based　case　retrieval　system,　the　efficiency　of　case　retrieval　will　increase　as　the　number　of　cases　continue　to　lower.　In　this　paper,　a　multi-dimensional　case　retrieval　optimization　algorithm,　the　algorithm　through　the　multi-dimensional　case　dimensionality　reduction　into　clusters　of　two-dimensional　space,　using　a　two-dimensional　spatial　clustering　to　represent　a　collection　of　case,　and　this　two-dimensional　spatial　clustering　to　establish　the　R-tree　spatial　index,　by　the　two　retrieval　methods　to　the　multidimensional　case　retrieval.　Proved　that　the　method　not　only　improves　the　accuracy　of　case　retrieval,　but　also　greatly　improve　the　efficiency　of　case　retrieval.　©　2013　Springer-Verlag.