Encrypted　image　retrieval　is　a　promising　technique　for　achieving　data　confidentiality　and　searchability　the　in　cloud-assisted　Internet　of　Things　(IoT)　environment.　However,　most　of　the　existing　top-k　ranked　image　retrieval　solutions　have　low　retrieval　efficiency　and　may　leak　the　values　and　orders　of　similarity　scores　to　the　cloud　server.　Hence,　if　a　malicious　server　learns　user　background　information　through　some　improper　means,　then　the　malicious　server　can　potentially　infer　user　preferences　and　guess　the　most　similar　image　content　according　to　similarity　scores.　To　solve　the　above　challenges,　we　propose　a　privacy-preserving　threshold-based　image　retrieval　scheme　using　the　convolutional　neural　network　(CNN)　model　and　a　secure　k-nearest　neighbor　(kNN)　algorithm,　which　improves　the　retrieval　efficiency　and　prevents　the　cloud　server　from　learning　the　values　and　orders　of　similarity　scores.　Formal　security　analysis　shows　that　our　proposed　scheme　can　resist　both　ciphertext-only　attack　(COA)　and　chosen-plaintext　attack　(CPA),　and　extensive　experiments　demonstrate　that　our　proposed　scheme　is　efficient　and　feasible　for　real-world　data　sets.