Add an OCR layer over MS Word images (extracted from PDF)

I’m working on a PDF (that i created with LaTeX) and I need to convert in into a MS Word document, but keeping the *exactly* original typesetting and design.
Since all the converters from PDF to Word will break some stuff, I thought that it would be a good idea to

  • use the PDF as background in the Word file
  • add an OCR layer to select the text (I do not need to edit the text; just looking at it and adding some comments).

Is there any way to achieve that? Including PDF’s images into Word is easy, but I don’t know how to add an OCR layer over it.