A metadata model based on feature classification tree and composite network is proposed, and the large-scale medical equipment data are selected to build a model and the model is verified. The results show that the model can be classified according to the characteristics of different dimensions of large-scale medical equipment to achieve accurate and fast retrieval, and the model can be used to describe multiple types, heterogeneous and multi-domain data. To a certain extent, the study solves the problem of the difficulty of integration and fusion of various types of metadata information.