Add pipeline tag

This PR adds the `pipeline_tag: image-feature-extraction` to the model card metadata so the model can be discovered under the correct category on the Hugging Face Hub. The existing model card already contains the paper link, code link, usage instructions, preprocessing notes, and citation, so no further changes are needed.

README.md

@@ -1,15 +1,16 @@
 ---
+language:
+- en
 library_name: CAPTOR
 tags:
-  - medical
-  - radiology
-  - computed-tomography
-  - vision-language
-  - contrastive-learning
-  - 3d
-  - pytorch
-language:
-  - en
+- medical
+- radiology
+- computed-tomography
+- vision-language
+- contrastive-learning
+- 3d
+- pytorch
+pipeline_tag: image-feature-extraction
 ---
 
 # CAPTOR
@@ -92,4 +93,4 @@ CAPTOR builds on Merlin, Clinical-Longformer, torchvision's ResNet-152 and Total
       primaryClass={cs.CV},
       url={https://arxiv.org/abs/2610.14226}, 
 }
-```
+```